The design and implementation of observational studies is the topic of the next Center for Clinical and Translational Science and Training (CCTST) Grand Rounds from 11 a.m. to 1 p.m. Friday, March 16, in Medical Sciences Building Room 2351.
From 11 a.m. to noon, Donald B. Rubin, PhD, will present, "Design of Observational Studies." Rubin is the John L. Loeb Professor of Statistics at Harvard University.
His talk will explain the components of the potential outcomes framework for causal inference and the reasons why non-randomized (observational) studies should be designed to parallel randomized experiments.
Participants will learn about best practices for observational study design, including propensity matching and subclassification.
From noon to 1 p.m., Cassandra W. Pattanayak, PhD, and Maurizio Macaluso, MD, DrPH, will present, "Propensity Score Matching to Assess the Effect of Single versus Double Embryo Transfer for In Vitro Fertilization."
Pattanayak is a college fellow in statistics at Harvard University. Macaluso is director of the division of biostatistics and epidemiology at Cincinnati Children's and co-director of the CCTST BERD core.
Their talk will provide an example of observational study design in practice and the use of the propensity score matching technique which allows many background covariates to be taken into account simultaneously.